Making LLMs Work for Enterprise Data Tasks

Intel Large language models (LLMs) have shown strong performances on natural language (NL) comprehension tasks, from summarization to question answering. The power of these models comes from optimizing for simple self-supervised learning tasks such as next token prediction using massive public web texts as training data on a scalable and adaptive architecture. However, by construction, LLMs know little about enterprise database tables in the private data ecosystem, which differ substantially from web text in structure and content. Given LLMs' performance is tied to their training data [1], a crucial question is how useful they can be in improving enterprise database management and analysis tasks. To help contend with this question, we contribute (1) preliminary experimental results on the performance of LLMs for text-to-SQL and semantic column-type detection tasks on enterprise datasets and (2) a discussion of challenges and potential solutions for effectively utilizing LLMs in enterprise settings.